Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 289 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0006

Data Index: 269583 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0237. Min Act: -0.0006

Data Index: 122565 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0224. Min Act: -0.0006

Data Index: 915863 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0230. Min Act: -0.0006

Data Index: 914433 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0209. Min Act: -0.0006

Data Index: 960935 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1291582 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0213. Min Act: -0.0006

Data Index: 454942 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1070088 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0213. Min Act: -0.0006

Data Index: 944719 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0007

Data Index: 603667 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1265126 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1298092 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1328054 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0206. Min Act: -0.0006

Data Index: 915827 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0205. Min Act: -0.0006

Data Index: 575342 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0212. Min Act: -0.0006

Data Index: 544155 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0197. Min Act: -0.0006

Data Index: 676536 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0201. Min Act: -0.0006

Data Index: 878987 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0201. Min Act: -0.0006

Data Index: 744411 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0201. Min Act: -0.0006

Data Index: 941024 (C4 (Web Text))

Max Activating Token Index: 500